paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-07-28 18:24:38 -05:00
Code Issues Packages Projects Releases Wiki Activity

Fixes some sample test files showing as modified after running tests

Browse Source
This commit is contained in:
Trenton H
2023-01-04 09:01:23 -08:00
parent 8e83f90952
commit d7939ca958
2 changed files with 38 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files

43
src/paperless_tesseract/tests/test_parser.py
View File

@@ -573,15 +573,18 @@ class TestParser(DirectoriesMixin, TestCase):
- Text from all pages extracted
"""
parser = RasterisedDocumentParser(None)
parser.parse(
os.path.join(self.SAMPLE_FILES, "multi-page-images-alpha.tiff"),
"image/tiff",
)
self.assertTrue(os.path.isfile(parser.archive_path))
self.assertContainsStrings(
parser.get_text().lower(),
["page 1", "page 2", "page 3"],
)
sample_file = os.path.join(self.SAMPLE_FILES, "multi-page-images-alpha.tiff")
with tempfile.NamedTemporaryFile() as tmp_file:
shutil.copy(sample_file, tmp_file.name)
parser.parse(
tmp_file.name,
"image/tiff",
)
self.assertTrue(os.path.isfile(parser.archive_path))
self.assertContainsStrings(
parser.get_text().lower(),
["page 1", "page 2", "page 3"],
)
def test_multi_page_tiff_alpha_srgb(self):
"""
@@ -595,15 +598,21 @@ class TestParser(DirectoriesMixin, TestCase):
- Text from all pages extracted
"""
parser = RasterisedDocumentParser(None)
parser.parse(
os.path.join(self.SAMPLE_FILES, "multi-page-images-alpha-rgb.tiff"),
"image/tiff",
)
self.assertTrue(os.path.isfile(parser.archive_path))
self.assertContainsStrings(
parser.get_text().lower(),
["page 1", "page 2", "page 3"],
sample_file = os.path.join(
self.SAMPLE_FILES,
"multi-page-images-alpha-rgb.tiff",
)
with tempfile.NamedTemporaryFile() as tmp_file:
shutil.copy(sample_file, tmp_file.name)
parser.parse(
tmp_file.name,
"image/tiff",
)
self.assertTrue(os.path.isfile(parser.archive_path))
self.assertContainsStrings(
parser.get_text().lower(),
["page 1", "page 2", "page 3"],
)
def test_ocrmypdf_parameters(self):
parser = RasterisedDocumentParser(None)